Educational Big Data Mining: Student Academic Performance Predictive Model Using Machine Learning Approaches

Lee, Shi Hock (2023) Educational Big Data Mining: Student Academic Performance Predictive Model Using Machine Learning Approaches. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text RSW_Lee Shi Hock_Fulltext.pdf Restricted to Registered users only Download (1MB)

Abstract

Utilization of Educational Data Mining (EDM) can be useful in predicting academic performance of students to mitigate student attrition rate, allocation of resources and aid in decision making processes for Higher Education Institution. This paper uses Programme for International Student Assessment (PISA) big dataset that consists of 612,004 participants from 79 countries, supported by machine learning approach to predict student academic performance. Unlike most literature that is confined in one geographical location or with limited datasets and factors, this paper study other factors that contribute towards academic success and uses students’ data from various backgrounds. The accuracy of the proposed model to predict student performance achieved 74%. It is discovered that gradient boosted trees surpass the other classification models that were considered (Logistic Regression, Naïve Bayes, Deep Learning, Random Forest, Fast Large Margin, Generalized Linear Model, Decision Tree and Support Vector Machine). Reading skills and habits have the highest significance importance in predicting academic performance of student